Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    RUN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Colombia
    -0.07
     helt
    -0.07
    jours
    -0.07
     également
    -0.06
     telegram
    -0.06
     cold
    -0.06
     ignorant
    -0.06
    کل
    -0.06
    _Message
    -0.06
    Scaling
    -0.06
    POSITIVE LOGITS
    COPY
    0.11
    RUN
    0.09
    ▍▍▍▍
    0.08
     attend
    0.07
    .↵↵↵↵↵
    0.07
    那些
    0.06
     "("
    0.06
     факти
    0.06
    „A
    0.06
    ("**
    0.06
    Act Density 0.005%

    No Known Activations